other,5-1-P01-1007,bq |
theoretical study of the
<term>
range concatenation
|
grammar
|
[ RCG ] formalism
</term>
has revealed many
|
#1604
The theoretical study of the range concatenation grammar [RCG] formalism has revealed many attractive properties which may be used in NLP. |
lr,11-3-P01-1007,bq |
<term>
RCG
</term>
, any
<term>
tree adjoining
|
grammar
|
</term>
can be parsed in
<term>
O ( n6 ) time
|
#1668
For example, after translation into an equivalent RCG, any tree adjoining grammar can be parsed in O(n6) time. |
model,11-6-P01-1007,bq |
method
</term>
on a
<term>
wide coverage English
|
grammar
|
</term>
are given . While
<term>
paraphrasing
|
#1749
The results of a practical evaluation of this method on a wide coverage English grammar are given. |
other,9-2-P01-1047,bq |
leads to a neat relation to
<term>
categorial
|
grammar
|
</term>
, ( yielding a treatment of
<term>
|
#1956
Our logical definition leads to a neat relation to categorial grammar, (yielding a treatment of Montague semantics), a parsing-as-deduction in a resource sensitive logic, and a learning algorithm from structured data (based on a typing-algorithm and type-unification). |
other,15-2-P05-1067,bq |
probabilistic synchronous dependency insertion
|
grammar
|
</term>
.
<term>
Synchronous dependency insertion
|
#9443
In this paper, we present a syntax-based statistical machine translation system based on a probabilistic synchronous dependency insertion grammar. |
other,9-4-P05-1067,bq |
<term>
approach
</term>
to inducing such a
<term>
|
grammar
|
</term>
from
<term>
parallel corpora
</term>
|
#9469
We first introduce our approach to inducing such agrammar from parallel corpora. |
other,12-3-P06-1018,bq |
powerful enough to strongly simulate many
<term>
|
grammar
|
formalisms
</term>
, such as
<term>
rewriting
|
#11101
This formalism is both elementary and powerful enough to strongly simulate manygrammar formalisms, such as rewriting systems, dependency grammars, TAG, HPSG and LFG. |
tech,22-1-P06-2001,bq |
checker
</term>
to be integrated in a
<term>
|
grammar
|
checker
</term>
for
<term>
Basque
</term>
. After
|
#11222
In this paper, we describe the research using machine learning techniques to build a comma checker to be integrated in agrammar checker for Basque. |
other,5-4-J82-3002,bq |
</term>
. With the aid of a
<term>
logic-based
|
grammar
|
formalism
</term>
called
<term>
extraposition
|
#12892
With the aid of a logic-based grammar formalism called extraposition grammars, Chat-80 translates English questions into the Prolog subset of logic. |
other,1-3-P84-1047,bq |
are grouped together . Like
<term>
semantic
|
grammar
|
</term>
, this allows easy exploitation of
|
#13352
Like semantic grammar, this allows easy exploitation of limited domain semantics. |
other,0-1-P86-1038,bq |
formalisms
</term>
.
<term>
Unification-based
|
grammar
|
formalisms
</term>
use structures containing
|
#14624
Unification-based grammar formalisms use structures containing sets of features to describe linguistic objects. |
tech,4-1-C90-1013,bq |
article introduces a
<term>
bidirectional
|
grammar
|
generation system
</term>
called
<term>
feature
|
#16215
This article introduces a bidirectional grammar generation system called feature structure-directed generation, developed for a dialogue translation system. |
other,1-4-C90-1013,bq |
the
<term>
derivation tree
</term>
. The
<term>
|
grammar
|
</term>
for this
<term>
generator
</term>
is
|
#16266
Thegrammar for this generator is designed to properly generate the speaker's intention in a telephone dialogue. |
other,14-1-C90-3014,bq |
system
</term>
using the
<term>
unification-based
|
grammar
|
formalism
</term>
:
<term>
Korean Phonology
|
#16370
This paper describes the framework of a Korean phonological knowledge base system using the unification-based grammar formalism: Korean Phonology Structure Grammar (KPSG). |
other,2-3-H90-1016,bq |
sentence hypotheses
</term>
. To avoid
<term>
|
grammar
|
coverage problems
</term>
we use a
<term>
fully-connected
|
#16905
To avoidgrammar coverage problems we use a fully-connected first-order statistical class grammar. |
other,8-3-H90-1016,bq |
fully-connected first-order statistical class
|
grammar
|
</term>
. The
<term>
speech-search algorithm
|
#16915
To avoid grammar coverage problems we use a fully-connected first-order statistical class grammar. |
lr,20-4-H90-1060,bq |
word error rate
</term>
on a standard
<term>
|
grammar
|
</term>
and
<term>
test set
</term>
from the
<term>
|
#17090
With only 12 training speakers for SI recognition, we achieved a 7.5% word error rate on a standardgrammar and test set from the DARPA Resource Management corpus. |
tech,8-1-C92-2068,bq |
expensive part of
<term>
unification-based
|
grammar
|
parsing
</term>
. We focus on one speed-up
|
#17955
Graph unification remains the most expensive part of unification-based grammar parsing. |
other,10-4-H92-1026,bq |
contrast to the usual approach of further
<term>
|
grammar
|
</term>
tailoring via the usual
<term>
linguistic
|
#18991
This stands in contrast to the usual approach of furthergrammar tailoring via the usual linguistic introspection in the hope of generating the correct parse. |
lr,28-5-H92-1060,bq |
sentences
</term>
were not covered by the
<term>
|
grammar
|
</term>
. We also report here on the performance
|
#19496
It was clear that the robust parser allowed us to answer many more questions correctly, as over a third of the sentences were not covered by thegrammar. |